filesystem-context

Persist agent context, plans, and tool outputs to disk files.

Updated Mar 22, 2026

Search Tags:#filesystem #context-management #agent-memory #tool-output #plan-persistence #scratch-pad

Ready to run

npx skills add https://github.com/AndrewChang-cpu/vibe-coding-configuration --skill filesystem-context-andrewchang-cpu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: filesystem-context
Source: https://github.com/AndrewChang-cpu/vibe-coding-configuration/tree/main/general-plugin/skills/filesystem-context
Command: npx skills add https://github.com/AndrewChang-cpu/vibe-coding-configuration --skill filesystem-context-andrewchang-cpu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Filesystems provide a durable, scalable store for growing agent context, enabling long-running tasks to access past tool outputs, memory, and scratch notes without bloating the active prompt.

Core Features & Use Cases

Offload large tool outputs to scratch files and reference them in context.
Persist agent plans, scratch pads, and learned preferences across sessions.
Coordinate sub-agent workspaces and dynamic skill loading for memory-efficient workflows.

Quick Start

Create a scratch workspace and begin offloading large tool outputs to files, referencing them in context as needed.

Frequently Asked Questions about filesystem-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I persist agent context to disk for long-running workflows?▼

You can persist agent context to disk by offloading large tool outputs and scratch notes to files, allowing long-running multi-turn agent workflows to access past memory without bloating the active prompt.

What is the best way to share state across sub-agents without exceeding the context window?▼

Sharing state across sub-agents is best handled by offloading data to a filesystem, enabling coordinated sub-agent workspaces and dynamic context loading for memory-efficient workflows.

How do I offload large tool outputs to scratch files for later reference?▼

You can offload large tool outputs to scratch files using a tool output handler, referencing these files in context later to prevent active prompt bloat during multi-turn tasks.

Can I persist agent plans and scratch pads across multiple sessions?▼

Yes, you can persist agent plans and scratch pads across sessions by writing them to the filesystem, ensuring learned preferences and task states remain accessible for future runs.

When do I need filesystem-based context management for agent memory?▼

Filesystem-based context management is needed for long-running, multi-turn agent workflows that require plan persistence, tool-output offloading, and state sharing across sub-agents.

Does this approach to agent memory support dynamic loading of skills?▼

Yes, the approach supports dynamic loading of skills by maintaining per-skill directories on disk, allowing agents to load required components and references on demand.